Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.358999967575073	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
51.57098627090454	10	30.45448514401138	2.9393215118189358	37.004863504029345	24.20968092419207	1000000	0.8731768386041672	0.5
93.67745780944824	20	193.01971986398806	3.868940181275106	200.14759797220904	180.06099711632123	2000000	0.9632717574493059	0.5
134.4154908657074	30	294.2985743677224	3.103184269368768	301.08421616244595	286.5592527851695	3000000	1.0694874344456513	0.5
174.29829382896423	40	333.7470691248036	2.516301718826556	338.8571883086115	326.63576889474643	4000000	1.1342988210849743	0.5
215.05413675308228	50	341.9326362669351	2.5246442251255043	348.62878870987333	336.2766696275794	5000000	1.1170686993907402	0.5
254.7115228176117	60	347.29517954056763	2.1580219272901737	352.4737883066555	342.0628803311847	6000000	1.0895082494580925	0.5
294.9059410095215	70	349.2919975316088	2.0101128875908643	354.78916400962044	345.48409542869194	7000000	1.060462458774185	0.5
334.8470194339752	80	352.5406541098441	1.8438585355151753	356.9263534063939	347.8694983861642	8000000	1.0359892893425384	0.5
374.042680978775	90	350.71461369011723	1.7889446996958116	357.0688081337139	346.49637881619856	9000000	1.0146923762488558	0.5
414.1832206249237	100	353.9819160413613	2.08176973190095	357.97031276789494	348.98999145720154	10000000	1.0032984759404815	0.5
